Approach for Dynamic Flight Pricing Based on Strategy Learning

Min LU; Yaoyuan ZHANG; Chun LU

doi:10.11999/JEIT200778

Volume 43 Issue 4

Apr. 2021

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2021 > 43(4): 1022-1028

Min LU, Yaoyuan ZHANG, Chun LU. Approach for Dynamic Flight Pricing Based on Strategy Learning[J]. Journal of Electronics & Information Technology, 2021, 43(4): 1022-1028. doi: 10.11999/JEIT200778

Citation:

Min LU, Yaoyuan ZHANG, Chun LU. Approach for Dynamic Flight Pricing Based on Strategy Learning[J]. Journal of Electronics & Information Technology, 2021, 43(4): 1022-1028. doi: 10.11999/JEIT200778

Min LU, Yaoyuan ZHANG, Chun LU. Approach for Dynamic Flight Pricing Based on Strategy Learning[J]. Journal of Electronics & Information Technology, 2021, 43(4): 1022-1028. doi: 10.11999/JEIT200778

Citation:

Min LU, Yaoyuan ZHANG, Chun LU. Approach for Dynamic Flight Pricing Based on Strategy Learning[J]. Journal of Electronics & Information Technology, 2021, 43(4): 1022-1028. doi: 10.11999/JEIT200778

PDF( 1578 KB)

Approach for Dynamic Flight Pricing Based on Strategy Learning

doi: 10.11999/JEIT200778

Min LU^{1
,
,},
Yaoyuan ZHANG¹,
Chun LU²

1.
College of Computer Science and Technology, Civil Aviation University of China, Tianjin 300300, China
2.
Information Center of China Southern Air Holding Company Limited, Guangzhou 510000, China

Funds: The National Natural Science Foundation of China (61502499), The Project from Key Laboratory of Artificial Intelligence for Airlines, CAAC

Received Date: 2020-09-20
Rev Recd Date: 2021-02-04

Available Online: 2021-03-02

Publish Date: 2021-04-20

Abstract

Abstract

The core of the dynamic flight pricing is to yield a pricing strategy with maximum seat revenue. The state-of-the-art flight pricing approaches are built on forecasting the fare demand. They suffer low profit due to the inaccurate prediction. To tackle the above issue, an approach for dynamic flight pricing based on strategy learning is proposed. That approach resorts to reinforcement learning to output pricing strategy with the highest expected return. That strategy is learned by iteratively policy evaluation and policy improvement. The rate of profit improvement on the two flights is empirically 30.94% and 39.96% over the existing pricing strategy, while that rate is 6.04% and 3.36% over the demand forecasting algorithm.
- Revenue management,
- Dynamic flight pricing,
- Reinforcement learning,
- Strategy learning

FullText(HTML)

References(16)

References

SMITH B C, LEIMKUHLER J F, and DARROW R M. Yield management at American airlines[J]. Interfaces, 1992, 22(1): 8–31. doi: 10.1287/inte.22.1.8

GALLEGO G and VAN RYZIN G. Optimal dynamic pricing of inventories with stochastic demand over finite horizons[J]. Management Science, 1994, 40(8): 999–1020. doi: 10.1287/mnsc.40.8.999

OTERO D F and AKHAVAN-TABATABAEI R. A stochastic dynamic pricing model for the multiclass problems in the airline industry[J]. European Journal of Operational Research, 2015, 242(1): 188–200. doi: 10.1016/j.ejor.2014.09.038

DELAHAYE T, ACUNA-AGOST R, BONDOUX N, et al. Data-driven models for itinerary preferences of air travelers and application for dynamic pricing optimization[J]. Journal of Revenue and Pricing Management, 2017, 16(6): 621–639. doi: 10.1057/s41272-017-0095-z

高金敏, 乐美龙, 曲林迟, 等. 基于时变需求的机票动态定价研究[J]. 南京航空航天大学学报, 2018, 50(4): 570–576. doi: 10.16356/j.1005-2615.2018.04.020

GAO Jinmin, LE Meilong, QU Linchi, et al. Dynamic pricing of air tickets based on time-varying demand[J]. Journal of Nanjing University of Aeronautics &Astronautics, 2018, 50(4): 570–576. doi: 10.16356/j.1005-2615.2018.04.020

SELC̣UK A M and AVṢAR Z M. Dynamic pricing in airline revenue management[J]. Journal of Mathematical Analysis and Applications, 2019, 478(2): 1191–1217. doi: 10.1016/j.jmaa.2019.06.012

LIN K Y and SIBDARI S Y. Dynamic price competition with discrete customer choices[J]. European Journal of Operational Research, 2009, 197(3): 969–980. doi: 10.1016/j.ejor.2007.12.040

施飞, 陈森发. 随时间变化的机票折扣定价研究[J]. 交通运输系统工程与信息, 2010, 10(1): 112–116. doi: 10.3969/j.issn.1009-6744.2010.01.017

SHI Fei and CHEN Senfa. Air ticket discount pricing based on time varying[J]. Journal of Transportation Systems Engineering and Information Technology, 2010, 10(1): 112–116. doi: 10.3969/j.issn.1009-6744.2010.01.017

LEE J, LEE E and KIM J. Electric vehicle charging and discharging algorithm based on reinforcement learning with data-driven approach in dynamic pricing scheme[J]. Energies, 2020, 13(8): 1950. doi: 10.3390/en13081950

CHENG Yin, ZOU Luobao, ZHUANG Zhiwei, et al. An extensible approach for real-time bidding with model-free reinforcement learning[J]. Neurocomputing, 2019, 360: 97–106. doi: 10.1016/j.neucom.2019.06.009

陈前斌, 谭颀, 魏延南, 等. 异构云无线接入网架构下面向混合能源供应的动态资源分配及能源管理算法[J]. 电子与信息学报, 2020, 42(6): 1428–1435. doi: 10.11999/JEIT190499

CHEN Qianbin, TAN Qi, WEI Yannan, et al. Dynamic resource allocation and energy management algorithm for hybrid energy supply in heterogeneous cloud radio access networks[J]. Journal of Electronics &Information Technology, 2020, 42(6): 1428–1435. doi: 10.11999/JEIT190499

GOSAVII A, BANDLA N, and DAS T K. A reinforcement learning approach to a single leg airline revenue management problem with multiple fare classes and overbooking[J]. IIE Transactions, 2002, 34(9): 729–742. doi: 10.1080/07408170208928908

SHIHAB S A M, LOGEMANN C, THOMAS D G, et al. Autonomous airline revenue management: A deep reinforcement learning approach to seat inventory control and overbooking[C]. The 36th International Conference on Machine Learning, Long Beach, USA, 2019: 132–139.

QIU Qinfu and CHEN Xiong. Behaviour-driven dynamic pricing modelling via hidden Markov model[J]. International Journal of Bio-Inspired Computation, 2018, 11(1): 27–33. doi: 10.1504/IJBIC.2018.090071

LAWHEAD R J and GOSAVI A. A bounded actor-critic reinforcement learning algorithm applied to airline revenue management[J]. Engineering Applications of Artificial Intelligence, 2019, 82: 252–262. doi: 10.1016/j.engappai.2019.04.008

RAMASWAMY A and BHATNAGAR S. Stability of stochastic approximations with “controlled markov” noise and temporal difference learning[J]. IEEE Transactions on Automatic Control, 2019, 64(6): 2614–2620. doi: 10.1109/TAC.2018.2874687

Relative Articles

Supplements(0)

Cited By

Proportional views